A keyword belongs to the transactional category

[Ashik Sarkar9]

transactional intent chart
Here you can see the inside of the new search intent model and how decisions are made. It is shown in a slightly simplified form.

The graph reads as follows:

On the ordinate axis are the most important characteristics for determining whether a keyword belongs to the transactional category. oman telegram
The x-axis shows the impact of individual characteristics on the model output, ranging from negative to positive. The vertical line separates negative from positive impact.
Each dot corresponds to a keyword. The color of the dot corresponds to the value of the feature corresponding to that keyword. Red means a high value, blue a low value.
Transactional intent
The graph in the previous paragraph showed which characteristics determine whether search intent is transactional. Let's examine this graph and take AdWords competition (competition_adwords) as an example.

Next to competition_adowrds in the graph, the red dots are to the right of the vertical line. This means that high competition in AdWords (a red dot) makes it more likely to be a transactional keyword (to the right of the vertical line).

On the other hand, look for the presence of a featured snippet ( pagefeaturedsnippet ). If this value is high (red dot) it means that there is a featured snippet in the SERP. The red dots are all to the left of the vertical line. This means that it is less likely to be a transactional keyword when there is a featured snippet.

Another thing you can see from the graph is that if Amazon is present one or more times ( urlscountamazon .) the SERP is more likely to be transactional and the opposite is true for Wikipedia.

These results are not surprising. What is interesting is that the machine learning model has not been given any information in advance. It has inferred it from the data. Furthermore, it has inferred the relationship between the different features. Note that the points are spread out on the x-axis rather than on top of each other. This is because the impact of SERP features on the model depends on what other features are present in the SERP. So, just because there is a lot of competition in AdWords, the model will not necessarily conclude that the keyword is transactional.

Informative intention
At the other end of the spectrum, you can look at the top twenty characteristics that determine whether intent is informational.


informational intent chart
Here you can see that high competition in AdWords means that informational intent is unlikely. You can also see that features like video carousels , related questions , and featured snippets are prevalent in SERPs with informational intent.

On the other hand, the word "best" usually indicates a commercial rather than informative intention. The same goes for the review function of SERPs and local results ( pagemapslocal ).

Another interesting fact is that when Facebook is part of the SERP, it is not usually intended for information purposes, but rather for navigation. It is more of a navigational intention.

Attempt to navigate
The following graphic shows navigation intent.


navigational intent chart
Obviously, sitelinks are often associated with navigational intent. You can also see that knowledge panels are often present for keywords with navigational intent. But they are also often present for informational keywords.

LinkedIn, Twitter, and Facebook typically appear in SERPs with navigational intent. Local results and about results are also associated with navigational intent. Note that local results are also associated with commercial intent based on context.

There typically won't be much competition in AdWords, featured snippets, or thumbnails for navigational intent.

But keep in mind that there is always an exception to every rule. And you can easily have a keyword with navigational intent that has characteristics that show other intents. The charts and examples provide general guidance for each type of intent.

You will also notice that unlike most other approaches to search intent, AccuRanker's model features can be interdependent and can also make one type of search intent less likely. Building such a model is possible using AccuRanker's vast data set in combination with advanced machine learning techniques.

Commercial search
In the case of commercial intent, you will mainly see the elements we have already described.


commercial intent chart
More specifically, local results (maps_local) are often associated with commercial intent. The same can be said for words like "top" and "best" and SERP features like FAQs and reviews .

On the other hand, words like "buy" or "sell" do not usually appear, nor do domains like Amazon, Facebook or Wikipedia.

To finish
This article has given you an insight into AccuRanker’s new AI-powered search intent feature. The components of how the model works and what kind of features affect different types of search intent, both positively and negatively, have been introduced.

The new search intent feature isn’t told or taught any rules. Instead, the model discovers its own rules by comparing patterns to a large number of examples. Simply put, the new search intent model learns from data. Having accurate search intent labels makes it possible to group and target keywords by intent. And this is paramount when creating content.